Region Graph Embedding Network for Zero-Shot Learning

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12349)


Most of the existing Zero-Shot Learning (ZSL) approaches learn direct embeddings from global features or image parts (regions) to the semantic space, which, however, fail to capture the appearance relationships between different local regions within a single image. In this paper, to model the relations among local image regions, we incorporate the region-based relation reasoning into ZSL. Our method, termed as Region Graph Embedding Network (RGEN), is trained end-to-end from raw image data. Specifically, RGEN consists of two branches: the Constrained Part Attention (CPA) branch and the Parts Relation Reasoning (PRR) branch. CPA branch is built upon attention and produces the image regions. To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch. To train our model, we introduce both a transfer loss and a balance loss to contrast class similarities and pursue the maximum response consistency among seen and unseen outputs, respectively. Extensive experiments on four datasets well validate the effectiveness of the proposed method under both ZSL and generalized ZSL settings.


Zero-shot learning Parts relation reasoning Balance loss 



This work was supported by the National Natural Science Foundation of China (Nos. 61702163 and 61976116), the Fundamental Research Funds for the Central Universities (Nos. 30920021135), and the Key Project of Shenzhen Municipal Technology Research (Nos. JSGG20200103103401723).

Supplementary material

504439_1_En_33_MOESM1_ESM.pdf (9.4 mb)
Supplementary material 1 (pdf 9583 KB)


  1. 1.
    Akata, Z., Malinowski, M., Fritz, M., Schiele, B.: Multi-cue zero-shot learning with strong supervision. In: CVPR (2016)Google Scholar
  2. 2.
    Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for attribute-based classification. In: CVPR (2013)Google Scholar
  3. 3.
    Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for image classification. In: TPAMI (2016)Google Scholar
  4. 4.
    Akata, Z., Reed, S., Walter, D., Lee, H., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: CVPR (2015)Google Scholar
  5. 5.
    Annadani, Y., Biswas, S.: Preserving semantic relations for zero-shot learning. In: CVPR (2018)Google Scholar
  6. 6.
    Cacheux, Y., Borgne, H., Crucianu, M.: Modeling inter and intra-class relations in the triplet loss for zero-shot learning. In: ICCV (2019)Google Scholar
  7. 7.
    Changpinyo, S., Chao, W.L., Gong, B., Sha, F.: Synthesized classifiers for zero-shot learning. In: CVPR (2016)Google Scholar
  8. 8.
    Chao, W.-L., Changpinyo, S., Gong, B., Sha, F.: An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 52–68. Springer, Cham (2016). Scholar
  9. 9.
    Chen, L., Zhang, H., Xiao, J., Liu, W., Chang, S.F.: Zero-shot visual recognition using semantics-preserving adversarial embedding network. In: CVPR (2018)Google Scholar
  10. 10.
    Elhoseiny, M., Elfeki, M.: Creativity inspired zero-shot learning. In: ICCV (2019)Google Scholar
  11. 11.
    Elhoseiny, M., Zhu, Y., Zhang, H., Elgammal, A.M.: Link the head to the "beak": zero shot learning from noisy text description at part precision. In: CVPR (2017)Google Scholar
  12. 12.
    Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR (2009)Google Scholar
  13. 13.
    Felix, R., Kumar, V.B., Reid, I., Carneiro, G.: Multi-modal cycle-consistent generalized zero-shot learning. In: ECCV (2008)Google Scholar
  14. 14.
    Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., T. Mikolov, E.A.: DeViSE: a deep visual-semantic embedding model. In: NeurIPS (2013)Google Scholar
  15. 15.
    Fu, Y., Hospedales, T.M., Xiang, T., Gong, S.: Transductive multi-view zero-shot learning. In: TPAMI (2015)Google Scholar
  16. 16.
    Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)Google Scholar
  17. 17.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  18. 18.
    Jayaraman, D., Grauman, K.: Zero-shot recognition with unreliable attributes. In: NeurIPS (2014)Google Scholar
  19. 19.
    Jiang, H., Wang, R., Shan, S., Chen, X.: Transferable contrastive network for generalized zero-shot learning. In: ICCV (2019)Google Scholar
  20. 20.
    Kampffmeyer, M., Chen, Y., Liang, X., Wang, H., Zhang, Y., Xing, E.: Rethinking knowledge graph propagation for zero-shot learning. In: CVPR (2019)Google Scholar
  21. 21.
    Kipf, T., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv:1609.02907 (2016)
  22. 22.
    Kodirov, E., Xiang, T., Fu, Z., Gong, S.: Unsupervised domain adaptation for zero-shot learning. In: ICCV (2015)Google Scholar
  23. 23.
    Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: CVPR (2017)Google Scholar
  24. 24.
    Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: CVPR (2009)Google Scholar
  25. 25.
    Li, X., Yang, F., Cheng, H., Liu, W., Shen, D.: Contour knowledge transfer for salient object detection. In: ECCV (2018)Google Scholar
  26. 26.
    Li, Y., Zhang, J., Zhang, J., Huang, K.: Discriminative learning of latent features for zero-shot recognition. In: CVPR (2018)Google Scholar
  27. 27.
    Liu, S., Long, M., Wang, J., Jordan, M.: Generalized zero-shot learning with deep calibration network. In: NeurIPS (2018)Google Scholar
  28. 28.
    Liu, Y., Guo, J., Cai, D., He, X.: Attribute attention for semantic disambiguation in zero-shot learning. In: ICCV (2019)Google Scholar
  29. 29.
    Long, Y., Liu, L., Shen, F., Shao, L., Li, X.: Zero-shot learning using synthesised unseen visual data with diffusion regularisation. In: TPAMI (2017)Google Scholar
  30. 30.
    Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., Porikli, F.: See more, know more: unsupervised video object segmentation with co-attention siamese networks. In: CVPR (2019)Google Scholar
  31. 31.
    Lu, X., Wang, W., Martin, D., Zhou, T., Shen, J., Luc, V.G.: Video object segmentation with episodic graph memory networks. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)Google Scholar
  32. 32.
    Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. JMLR 9, 2579–2605 (2008)zbMATHGoogle Scholar
  33. 33.
    Morgado, P., Vasconcelos, N.: Semantically consistent regularization for zero-shot recognition. In: CVPR (2017)Google Scholar
  34. 34.
    Norouzi, M., et al.: Zero-shot learning by convex combination of semantic embeddings. In: NeurIPS (2014)Google Scholar
  35. 35.
    Palatucci, M., Pomerleau, D., Hinton, G.E., Mitchell, T.M.: Zero-shot learning with semantic output codes. In: NeurIPS (2009)Google Scholar
  36. 36.
    Patterson, G., Hays, J.: Sun attribute database: discovering, annotating, and recognizing scene attributes. In: CVPR (2012)Google Scholar
  37. 37.
    Qiao, R., Liu, L., Shen, C., van den Hengel, A.: Less is more: zero-shot learning from online textual documents with noise suppression. In: CVPR (2016)Google Scholar
  38. 38.
    Reed, S., Akata, Z., Lee, H., Schiele, B.: Learning deep representations of fine-grained visual descriptions. In: CVPR (2016)Google Scholar
  39. 39.
    Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: ICML (2015)Google Scholar
  40. 40.
    Shen, Y., Qin, J., Huang, L., Liu, L., Zhu, F., Shao, L.: Invertible zero-shot recognition flows. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)Google Scholar
  41. 41.
    Socher, R., Ganjoo, M., Manning, C.D., Ng, A.: Zero-shot learning through cross-modal transfer. In: NeurIPS (2013)Google Scholar
  42. 42.
    Song, J., Shen, C., Yang, Y., Liu, Y., Song, M.: Transductive unbiased embedding for zero-shot learning. In: CVPR (2018)Google Scholar
  43. 43.
    Verma, V.K., Arora, G., Mishra, A., Rai, P.: Generalized zero-shot learning via synthesized examples. In: CVPR (2018)Google Scholar
  44. 44.
    Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset. In: Technical report (2011)Google Scholar
  45. 45.
    Wang, X., Ye, Y., Gupta, A.: Zero-shot recognition via semantic embeddings and knowledge graphs. In: CVPR (2018)Google Scholar
  46. 46.
    Wu, B., et al.: Tencent ml-images: a large-scale multi-label image database for visual representation learning. IEEE Access 7, 172683–172693 (2019)CrossRefGoogle Scholar
  47. 47.
    Wu, B., Jia, F., Liu, W., Ghanem, B., Lyu, S.: Multi-label learning with missing labels using mixed dependency graphs. Int. J. Comput. Vis. 126, 875–896 (2018)MathSciNetCrossRefGoogle Scholar
  48. 48.
    Xian, Y., Akata, Z., Sharma, G., Nguyen, Q., Hein, M., Schiele, B.: Latent embeddings for zero-shot classification. In: CVPR (2016)Google Scholar
  49. 49.
    Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: CVPR (2018)Google Scholar
  50. 50.
    Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning-the good, the bad and the ugly. In: CVPR (2017)Google Scholar
  51. 51.
    Xian, Y., Sharma, S., Saurabh, S., Akata, Z.: f-VAEGAN-D2: a feature generating framework for any-shot learning. In: CVPR (2019)Google Scholar
  52. 52.
    Xie, G.S., et al.: Attentive region embedding network for zero-shot learning. In: CVPR (2019)Google Scholar
  53. 53.
    Xie, G.S., Zhang, X.Y., Yang, W., Xu, M., Yan, S., Liu, C.L.: LG-CNN: from local parts to global discrimination for fine-grained recognition. Pattern Recogn. 71, 118–131 (2017)CrossRefGoogle Scholar
  54. 54.
    Xie, G.S., et al.: SRSC: selective, robust, and supervised constrained feature representation for image classification. IEEE Trans. Neural Netw. Learn. Syst. 31, 4290–4302 (2019)MathSciNetCrossRefGoogle Scholar
  55. 55.
    Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451–466. Springer, Cham (2016). Scholar
  56. 56.
    Xu, J., Zhao, R., Zhu, F., Wang, H., Ouyang, W.: Attention-aware compositional network for person re-identification. arXiv:1805.03344 (2018)
  57. 57.
    Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)Google Scholar
  58. 58.
    Yang, F.S.Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: CVPR (2018)Google Scholar
  59. 59.
    Yang, G., Liu, J., Xu, J., Li, X.: Dissimilarity representation learning for generalized zero-shot recognition. In: MM (2018)Google Scholar
  60. 60.
    Yao, Y., et al.: Exploiting web images for multi-output classification: from category to subcategories. IEEE Trans. Neural Netw. Learn. Syst. 31, 2348–2360 (2020)Google Scholar
  61. 61.
    Yao, Y., Zhang, J., Shen, F., Hua, X., Xu, J., Tang, Z.: Exploiting web images for dataset construction: a domain robust approach. IEEE Trans. Multimedia 19, 1771–1784 (2017)CrossRefGoogle Scholar
  62. 62.
    Ye, M., Guo, Y.: Zero-shot classification with discriminative semantic representation learning. In: CVPR (2017)Google Scholar
  63. 63.
    Yu, H., Lee, B.: Zero-shot learning via simultaneous generating and learning. In: NeurIPS (2019)Google Scholar
  64. 64.
    Yu, Y., Ji, Z., Fu, Y., Guo, J., Pang, Y., Zhang, Z.: Stacked semantics-guided attention model for fine-grained zero-shot learning. In: NeurIPS (2018)Google Scholar
  65. 65.
    Yu, Y., Ji, Z., Han, J., Zhang, Z.: Episode-based prototype generating network for zero-shot learning. In: CVPR (2020)Google Scholar
  66. 66.
    Zhang, L., Xiang, T., Gong, S., et al.: Learning a deep embedding model for zero-shot learning. In: CVPR (2017)Google Scholar
  67. 67.
    Zhang, L., et al.: Towards effective deep embedding for zero-shot learning. IEEE Trans. Circ. Syst. Video Technol. 30, 2843–2852 (2020)CrossRefGoogle Scholar
  68. 68.
    Zhang, L., et al.: Adaptive importance learning for improving lightweight image super-resolution network. Int. J. Comput. Vis. 128, 479–499 (2020)MathSciNetCrossRefGoogle Scholar
  69. 69.
    Zhang, L., et al.: Unsupervised domain adaptation using robust class-wise matching. IEEE Trans. Circ. Syst. Video Technol. 29, 1339–1349 (2018)CrossRefGoogle Scholar
  70. 70.
    Zhang, L., Wei, W., Bai, C., Gao, Y., Zhang, Y.: Exploiting clustering manifold structure for hyperspectral imagery super-resolution. IEEE Trans. Image Process. 27, 5969–5982 (2018)MathSciNetCrossRefGoogle Scholar
  71. 71.
    Zhang, L., Wei, W., Zhang, Y., Shen, C., Van Den Hengel, A., Shi, Q.: Cluster sparsity field: an internal hyperspectral imagery prior for reconstruction. Int. J. Comput. Vis. 126, 797–821 (2018)CrossRefGoogle Scholar
  72. 72.
    Zhang, Z., Saligrama, V.: Zero-shot learning via semantic similarity embedding. In: ICCV (2015)Google Scholar
  73. 73.
    Zhang, Z., Saligrama, V.: Zero-shot learning via joint latent similarity embedding. In: CVPR (2016)Google Scholar
  74. 74.
    Zhang, Z., Liu, L., Shen, F., Shen, H.T., Shao, L.: Binary multi-view clustering. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1774–1782 (2018)CrossRefGoogle Scholar
  75. 75.
    Zhao, F., Liao, S., Xie, G.S., Zhao, J., Zhang, K., Shao, L.: Unsupervised domain adaptation with noise resistible mutual-training for person re-identification. In: ECCV (2020)Google Scholar
  76. 76.
    Zhao, F., Zhao, J., Yan, S., Feng, J.: Dynamic conditional networks for few-shot learning. In: ECCV (2018)Google Scholar
  77. 77.
    Zhou, B., Khosla, A.A.L., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)Google Scholar
  78. 78.
    Zhu, P., Wang, H., Saligrama, V.: Generalized zero-shot recognition based on visually semantic embedding. In: CVPR (2019)Google Scholar
  79. 79.
    Zhu, Y., Elhoseiny, M., Liu, B., Peng, X., Elgammal, A.: A generative adversarial approach for zero-shot learning from noisy texts. In: CVPR (2018)Google Scholar
  80. 80.
    Zhu, Y., Xie, J., Tang, Z., Peng, X., Elgammal, A.: Learning where to look: semantic-guided multi-attention localization for zero-shot learning. In: NeurIPS (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Inception Institute of Artificial IntelligenceAbu DhabiUAE
  2. 2.Harbin Institute of TechnologyShenzhenChina
  3. 3.Peng Cheng LaboratoryShenzhenChina
  4. 4.Mohamed bin Zayed University of Artificial IntelligenceAbu DhabiUAE
  5. 5.Nanjing University of Science and TechnologyNanjingChina

Personalised recommendations